Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Dec 21;24(24):8180.
doi: 10.3390/s24248180.

Enhanced Detection of Leishmania Parasites in Microscopic Images Using Machine Learning Models

Michael Contreras-Ramírez  1 , Jhonathan Sora-Cardenas  1 , Claudia Colorado-Salamanca  2 , Clemencia Ovalle-Bracho  1 , Daniel R Suárez  1
Affiliations

Enhanced Detection of Leishmania Parasites in Microscopic Images Using Machine Learning Models

Michael Contreras-Ramírez et al. Sensors (Basel). .

Abstract

Cutaneous leishmaniasis is a parasitic disease that poses significant diagnostic challenges due to the variability of results and reliance on operator expertise. This study addresses the development of a system based on machine learning algorithms to detect Leishmania spp. parasite in direct smear microscopy images, contributing to the diagnosis of cutaneous leishmaniasis. Starting with acquiring and labeling 500 images, an experimental design was implemented, including preprocessing and segmentation techniques such as Otsu, local thresholding, and Iterative Global Minimum Search (IGMS) to improve parasite detection. The phenotypic features of the parasites were extracted, focusing on morphology, texture, and color. Machine learning models (ANN, SVM, and RF) optimized through Grid Search were applied for classification. The model with the best results was a Support Vector Machine (SVM), achieving a sensitivity of 91.87% and a specificity of 89.21% at the crop level. Compared with previous studies, these results highlight the relevance and consistency of the methodology used, supporting the initial hypothesis. This suggests that machine learning techniques offer a promising path toward improving the diagnosis of cutaneous leishmaniasis.

Keywords: cutaneous leishmaniasis; direct smear examination; grid search; machine learning; preprocessing; segmentation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Project methodology diagram.
Figure 2
Figure 2
Original direct smear image of cutaneous leishmaniasis with the presence of Leishmania amastigotes. Scale bar 10 µm.
Figure 3
Figure 3
Experimental design of preprocessing.
Figure 4
Figure 4
(a) Original image, (b) Image with 70-pixel border padding.
Figure 5
Figure 5
Average histograms of 500 images in color channels: (a) Color space (R, G, B), (b) Color space (H, S, V), (c) Grayscale.
Figure 6
Figure 6
Experimental design process applying Otsu segmentation: (a) Grayscale image, (b) Binarized image with Otsu, (c) Final ROI mask.
Figure 7
Figure 7
Experimental design process applying local threshold segmentation: (a) Grayscale image, (b) Binarized image with Local Threshold, (c) Final ROI mask.
Figure 8
Figure 8
Experimental design process applying IGMS segmentation: (a) Grayscale image, (b) Binarized image with IGMS, (c) Final ROI mask.
Figure 9
Figure 9
(a) Original cropped image, (b) K-means segmented image.
Figure 10
Figure 10
Structure extraction process using K-means segmentation: (a) Nucleus and kinetoplast mask, (b) Cytoplasm mask, (c) Background mask, (d) Final nucleus mask, (e) Final kinetoplast mask, (f) Final cytoplasm mask.
Figure 11
Figure 11
ROC of SVM, ANN, RF Models with “KNN Balanced” data.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. World Health Organization . Leishmaniasis. World Health Organization; Geneva, Switzerland: 2023.
    1. Pan American Health Organization and World Health Organization Interactive Atlas of Leishmaniasis in the Americas: Clinical Aspects and Differential Diagnosis. 2020. [(accessed on 16 December 2024)]. Available online: https://iris.paho.org/handle/10665.2/53166. - DOI
    1. Rosado L., Da Costa J.M.C., Elias D., Cardoso J.S. Automated Detection of Malaria Parasites on Thick Blood Smears via Mobile Devices. Procedia Comput. Sci. 2016;90:138–144. doi: 10.1016/j.procs.2016.07.024. - DOI
    1. Dave I.R. Image analysis for malaria parasite detection from microscopic images of thick blood smear; Proceedings of the 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET); Chennai, India. 22–24 March 2017.
    1. Delahunt C.B., Mehanian C., Hu L., McGuire S.K., Champlin C.R., Horning M.P., Wilson B.K., Thompon C.M. Automated microscopy and machine learning for expert-level malaria field diagnosis; Proceedings of the 2015 IEEE Global Humanitarian Technology Conference (GHTC); Seattle, WA, USA. 8–11 October 2015.

MeSH terms

LinkOut - more resources